MULTIMODAL EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR PREDICTIVE HEALTHCARE AND SMART DECISION-MAKING SYSTEMS IN PAKISTAN

Abstract

The increasing adoption of Artificial Intelligence (AI) in healthcare has transformed predictive analytics and clinical decision-making processes. However, the effectiveness of conventional AI systems is often constrained by limited transparency, interpretability, and trust among healthcare professionals. This study investigates the role of Multimodal Explainable Artificial Intelligence (MXAI) in enhancing predictive healthcare and smart decision-making systems in Pakistan. Drawing upon Socio-Technical Systems Theory, the study proposes a framework that integrates multimodal healthcare data, explainable AI mechanisms, predictive healthcare capabilities, and digital governance capacity. A quantitative research design was employed, and data were collected from healthcare professionals, healthcare administrators, information technology specialists, and policymakers across Pakistan. The proposed relationships were examined using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings revealed that MXAI significantly improves predictive healthcare capabilities and smart decision-making systems. Predictive healthcare capabilities were found to mediate the relationship between MXAI and smart decision-making, while digital governance capacity strengthened this relationship. The study contributes to the growing literature on explainable AI and healthcare informatics by providing empirical evidence from a developing-country context. The findings offer valuable insights for healthcare organizations, technology developers, and policymakers seeking to implement transparent, trustworthy, and data-driven healthcare systems. The study concludes that MXAI has substantial potential to support healthcare transformation, improve clinical outcomes, and strengthen intelligent decision-making within Pakistan's healthcare sector.